ClawHub
Back to skill

Security audit

Commitment and Consistency

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only thinking skill about commitment and consistency, with disclosed ethical framing and no executable or persistent behavior.

Install only if you want a persuasion and decision-analysis aid. Use it for transparent, voluntary, user-benefiting commitment paths with clear exits, and avoid applying it to coerce people, exploit prior commitments, or encourage physical risk or confrontation.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · examples/freedman-fraser-1966-cialdini-systematization-modern-applications.md (reported line 26)May include surrounding context.

md
>
> — Cialdini (1984/2006), p. 109.

This is the operational version of the [`sunk-cost-fallacy`](../skills/sunk-cost-fallacy/SKILL.md) defense applied to social commitments.

**Modern applications** are extensive:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This example explicitly teaches that a small verbal commitment can drive people to take disproportionate, even physically risky, follow-through actions, yet it frames the mechanism as a reusable design template without equally prominent safety guardrails. In the context of a persuasion skill, that omission increases the chance that readers apply the technique to pressure others into unsafe escalation or overlook the need to avoid scenarios involving physical confrontation, coercion, or impaired consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.